Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information

Kang Chen Tsinghua University Yu-Kun Lai Cardiff University Yu-XIn Wu Tsinghua University Ralph Martin Cardiff University Shi-Min Hu Tsinghua University

Geometric Modeling and Processing mathscidoc:1605.16002

ACM Transactions on Graphics, 33, (6)
We present a novel solution to automatic semantic modeling of indoor scenes from a sparse set of low-quality RGB-D images. Such data presents challenges due to noise, low resolution, occlusion and missing depth information. We exploit the knowledge in a scene database containing 100s of indoor scenes with over 10,000 manually segmented and labeled mesh models of objects. In seconds, we output a visually plausible 3D scene, adapting these models and their parts to fit the input scans. Contextual relationships learned from the database are used to constrain reconstruction, ensuring semantic compatibility between both object models and parts. Small objects and objects with incomplete depth information which are difficult to recover reliably are processed with a two-stage approach. Major objects are recognized first, providing a known scene structure. 2D contour-based model retrieval is then used to recover smaller objects. Evaluations using our own data and two public datasets show that our approach can model typical real-world indoor scenes efficiently and robustly.
Semantic modeling, 3D scenes, Model retrieval
[ Download ] [ 2016-05-17 23:36:05 uploaded by shimin ] [ 295 downloads ] [ 0 comments ] [ Cited by 21 ]
@inproceedings{kangautomatic,
  title={Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information },
  author={Kang Chen, Yu-Kun Lai, Yu-XIn Wu, Ralph Martin, and Shi-Min Hu},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160517233605767215034},
  booktitle={ACM Transactions on Graphics},
  volume={33},
  number={6},
}
Kang Chen, Yu-Kun Lai, Yu-XIn Wu, Ralph Martin, and Shi-Min Hu. Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information . Vol. 33. In ACM Transactions on Graphics. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160517233605767215034.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved